Neural Models for Sequence Chunking
arXiv:1701.04027
Abstract
Many natural language understanding (NLU) tasks, such as shallow parsing (i.e., text chunking) and semantic slot filling, require the assignment of representative labels to the meaningful chunks in a sentence. Most of the current deep neural network (DNN) based methods consider these tasks as a sequence labeling problem, in which a word, rather than a chunk, is treated as the basic unit for labeling. These chunks are then inferred by the standard IOB (Inside-Outside-Beginning) labels. In this paper, we propose an alternative approach by investigating the use of DNN for sequence chunking, and propose three neural models so that each chunk can be treated as a complete unit for labeling. Experimental results show that the proposed neural sequence chunking models can achieve start-of-the-art performance on both the text chunking and slot filling tasks.
Accepted by AAAI 2017
References in corpus (10)
- Convolutional Neural Networks for Sentence Classification
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Introduction to the CoNLL-2000 Shared Task: Chunking
- Multi-Task Cross-Lingual Sequence Tagging from Scratch
- Classifying Relations by Ranking with Convolutional Neural Networks
- Dependency-based Convolutional Neural Networks for Sentence Embedding
- Recurrent Neural Networks with External Memory for Language Understanding
- Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
- Encoder-decoder with Focus-mechanism for Sequence Labelling Based Spoken Language Understanding
Cited by in corpus (10)
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
- Deep Active Learning for Named Entity Recognition
- Text-based depression detection on sparse data
- Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding
- Prior Knowledge Driven Label Embedding for Slot Filling in Natural Language Understanding
- Sequence Labeling: A Practical Approach
- GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
- Chinese User Service Intention Classification Based on Hybrid Neural Network
- Character-Level Feature Extraction with Densely Connected Networks
- Deep Cascade Multi-task Learning for Slot Filling in Online Shopping Assistant